Kuan‐Ching Li

Kuan Li, Zhongwang Zhang, Huifeng Yin et al.

Transcending human cognitive limitations represents a critical frontier in LLM training. Proprietary agentic systems like DeepResearch have demonstrated superhuman capabilities on extremely complex information-seeking benchmarks such as BrowseComp, a feat previously unattainable. We posit that their success hinges on a sophisticated reasoning pattern absent in open-source models: the ability to systematically reduce extreme uncertainty when navigating vast information landscapes. Based on this insight, we introduce WebSailor, a complete post-training methodology designed to instill this crucial capability. Our approach involves generating novel, high-uncertainty tasks through structured sampling and information obfuscation, RFT cold start, and an efficient agentic RL training algorithm, Duplicating Sampling Policy Optimization (DUPO). With this integrated pipeline, WebSailor significantly outperforms all open-source agents in complex information-seeking tasks, matching proprietary agents' performance and closing the capability gap.

Liangcai Su, Zhen Zhang, Guangyu Li et al.

Large language models (LLMs) have evolved into agentic systems capable of autonomous tool use and multi-step reasoning for complex problem-solving. However, post-training approaches building upon general-purpose foundation models consistently underperform in agentic tasks, particularly in open-source implementations. We identify the root cause: the absence of robust agentic foundation models forces models during post-training to simultaneously learn diverse agentic behaviors while aligning them to expert demonstrations, thereby creating fundamental optimization tensions. To this end, we are the first to propose incorporating Agentic Continual Pre-training (Agentic CPT) into the deep research agents training pipeline to build powerful agentic foundational models. Based on this approach, we develop a deep research agent model named AgentFounder. We evaluate our AgentFounder-30B on 10 benchmarks and achieve state-of-the-art performance while retains strong tool-use ability, notably 39.9% on BrowseComp-en, 43.3% on BrowseComp-zh, and 31.5% Pass@1 on HLE.

Amir Javadpour, Samira Rezaei, Kuan-Ching Li et al.

Due to the fast-growing volume of text documents and reviews in recent years, current analyzing techniques are not competent enough to meet the users' needs. Using feature selection techniques not only support to understand data better but also lead to higher speed and also accuracy. In this article, the Whale Optimization algorithm is considered and applied to the search for the optimum subset of features. As known, F-measure is a metric based on precision and recall that is very popular in comparing classifiers. For the evaluation and comparison of the experimental results, PART, random tree, random forest, and RBF network classification algorithms have been applied to the different number of features. Experimental results show that the random forest has the best accuracy on 500 features. Keywords: Feature selection, Whale Optimization algorithm, Selecting optimal, Classification algorithm

Amir Jalilifard, Vinicius F. Caridá, Alex F. Mansano et al.

Keyword extraction has received an increasing attention as an important research topic which can lead to have advancements in diverse applications such as document context categorization, text indexing and document classification. In this paper we propose STF-IDF, a novel semantic method based on TF-IDF, for scoring word importance of informal documents in a corpus. A set of nearly four million documents from health-care social media was collected and was trained in order to draw semantic model and to find the word embeddings. Then, the features of semantic space were utilized to rearrange the original TF-IDF scores through an iterative solution so as to improve the moderate performance of this algorithm on informal texts. After testing the proposed method with 200 randomly chosen documents, our method managed to decrease the TF-IDF mean error rate by a factor of 50% and reaching the mean error of 13.7%, as opposed to 27.2% of the original TF-IDF.